跨社交网络的实体用户关联技术研究

doi:10.3969/j.issn.1671-1122.2017.02.008

信息网络安全 ›› 2017, Vol. 17 ›› Issue (2): 51-58.doi: 10.3969/j.issn.1671-1122.2017.02.008

跨社交网络的实体用户关联技术研究

罗梁¹, 王文贤^1,², 钟杰¹, 王海舟¹()

1.四川大学计算机学院网络与可信计算研究所,四川成都610065
2. 四川大学网络空间安全研究院,四川成都610065

收稿日期:2016-12-01 出版日期:2017-02-20 发布日期:2020-05-12
作者简介:
作者简介：罗梁（1992—）,男,湖北,硕士研究生,主要研究方向为数据挖掘、舆情安全等;王文贤（1978—）,男,福建,讲师,博士,主要研究方向为网络空间安全、舆情分析和挖掘;钟杰（1989—）,男,四川,硕士研究生,主要研究方向为社交网络、舆情分析;王海舟（1986—）,男,四川,讲师,博士,主要研究方向为网络空间安全、舆情分析和挖掘。
基金资助:
国家科技支撑计划[2012BAH18B05];国家自然科学基金 [61272447]

Research on Users Associated Technology across Social Network

Liang LUO¹, Wenxian WANG^1,², Jie ZHONG¹, Haizhou WANG¹()

1. Network and Trusted Computing Institute, College of Computer, Sichuan University, Chengdu Sichuan 610065,China
2. Cybersecurity Research Institute, Sichuan University, Chengdu Sichuan 610065, China)

Received:2016-12-01 Online:2017-02-20 Published:2020-05-12

摘要/Abstract

摘要：

近年来,随着社交网络大规模普及,社交网络在人们生活中扮演了越来越重要的角色。它们拥有海量的用户规模,但进行实名认证的用户却只占很小的比例,这使得恶意用户可以肆意散播各种谣言和不良信息,给互联网监管带来了巨大挑战。因此对跨社交网络的实体用户进行关联,建立身份识别信息网络,有助于解决用户的身份识别和监管问题。文章设计实现了针对QQ空间和新浪微博的信息采集系统,然后针对网络上采集到的544万微博用户和2459万QQ空间用户的资料和行为数据进行分析,提出了一种用户跨社交网站关联整体模型。该模型基于逻辑回归模型进行用户判定分类,同时根据SimRank算法的原理提出了SNC算法剔除噪声用户,提高模型精确度,最后利用本文筛选出的数据集进行跨社交网络用户关联实验。实验结果表明本模型能够筛选出关联性较强的用户对,经过剪枝处理后模型精确度有效提升,模型能够有效的对不同社交网络的用户进行关联。

关键词: 跨社交网络, 用户关联, 信息采集, SNC算法, 逻辑回归模型

Abstract:

With the massive popularity of social networks in recent years, social network has played a very important role in people’s daily lives. It has a lot of users, but few of them needs real name authentication, which malicious users can freely spread rumors and bad information to the public and bring challenges to Internet regulations. Therefore, associating entity users across different social networks, establish the network identification can help identify and supervise the users. The paper’s main research work are as follows. Firstly we designed a system to collect QZone and Weibo’s user’s information. Secondly we analyze the data we collect from the internet which contains 5,440,000 users of Weibo and 24,590,000 users of QZone. Then we proposed a model of users associated across social network. This model is based on logic regression model which is used to classify the users, at the same time, according to the principle of SimRank algorithm, the SNC algorithm is proposed to eliminate the noise and improve the accuracy of the model. Finally we use the model on the dataset we collected. The experimental result shows that the model can filter out pairs of users that associated strongly, the accuracy of the model has improved and the model can associate users of different social networks after pruning.

Key words: cross social networks, users association, information collection, SNC algorithm, logistic regression

中图分类号:

TP309

罗梁, 王文贤, 钟杰, 王海舟. 跨社交网络的实体用户关联技术研究[J]. 信息网络安全, 2017, 17(2): 51-58.

Liang LUO, Wenxian WANG, Jie ZHONG, Haizhou WANG. Research on Users Associated Technology across Social Network[J]. Netinfo Security, 2017, 17(2): 51-58.

图/表 12

图1

表1

图2

图3

图4

图5

图6

表2

表3

图7

图8

图9

参考文献 21

[1]	中国互联网信息中心. CNNIC中国互联网络发展状况统计报告[EB/OL]. .
[2]	BERTHONA P R, PITTB L F, PLANGGERB K, et al.Marketing Meets Web 2.0, Social Media, and Creative Consumers: Implications for International Marketing Strategy[J]. Business Horizons, 2012, 55(3): 261-271.
[3]	SMITH A N, FISCHER E, YONGJIAN C.How Does Brand-related User-generated Content Differ across YouTube, Facebook, and Twitter?[J]. Journal of Interactive Marketing, 2012, 26(2): 102-113.
[4]	REZA Z, LIU H.Connecting Users across Social Media Sites: A Behavioral-Modeling Approach[C]// Association for Computing Machinery. Proceedings of the 19th ACM Special Interest Group on Knowledge Discovery and Data Mining International Conference, August 11-14, 2013, Chicago, IL, USA. New York: ACM, 2013: 41-49.
[5]	AMERSHI S, FOGARTY J, WELD D S.Regroup: Interactive Machine Learning for on-demand Group Creation in Social Networks[C]// Association for Computing Machinery. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, May 5-10, 2012, Austin, Texas, USA. New York: ACM, 2012: 21-30.
[6]	IOFCIU T, FANKHAUSER P, ABEL F, et al.Identifying Users Across Social Tagging Systems[C]// Association for the Advancement of Artificial Intelligence. Proceedings of the 5th International Conference on Weblogs and Social Media, July 17-21, 2011, Barcelona, Spain. Palo Alto, California: AAAI. 2011: 17-21.
[7]	NISHIOKA C, GROßE-BÖLTING G, SCHERP A.Influence of Time on User Profiling and Recommending Researchers in Social Media [C]// Know-Center and Graz University of Technology. Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business,October 21-23, 2015, Graz, Austria . New York: ACM ICPS,2015: Article No. 9.
[8]	LU C, SHUAI H, YU P S.Identifying Your Customers in Social Networks[C]// Association for Computing Machinery. Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, November 3-7, 2014, Shanghai, China. New York: ACM, 2014: 391-400.
[9]	KONG X, ZHANG J, YU P S.Inferring Anchor Links across Multiple Heterogeneous Social Networks[C]// Association for Computing Machinery. Proceedings of the 22nd ACM international conference on Conference on information & knowledge management, October 27 - November 1, 2013, San Francisco, CA, USA. New York: ACM, 2013: 179-188.
[10]	CHUNG C, LIN C, LIN C, et al.Person Identification between Different Online Social Networks[C]// IEEE Computer Society. Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), Aug 11-14, 2014, Washington, DC, USA. Washington, DC, USA: IEEE Computer Society, 2014: 94-101.
[11]	VOSECKY J, HONG D, SHEN V Y.User Identification across Multiple Social Networks[C]// IEEE Computer Society. Proceedings of the 1st International Conference on Networked Digital Technologies, July 28-31, 2009, Ostrava, Czech Republic. Washington, DC, USA: IEEE Computer Society, 2009: 360-365.
[12]	CARMAGNOLA F, OSBORNE F, TORRE I.User Data Distributed on The Social Web: How to Identify Users on Different Social Systems and Collecting Data About Them[C]// Association for Computing Machinery. Proceedings of the 1st International Workshop on Information Heterogeneity and Fusion in Recommender Systems, September 26-30, 2010, Barcelona, Spain. New York: ACM, 2010: 9-15.
[13]	YE N, ZHAO Y, DONG L, et al.User Identification Based on Multiple Attribute Decision Making in Social Networks[J]. China Communications, 2013, 10(12): 37-49.
[14]	寇月,申德荣,刘恒,等.异构网络中关联实体识别模型及增量式验证算法研究[J].计算机学报,2013,36(10):2096-2108.
[15]	李航. 统计学习方法[M].北京:清华大学出版社,2012.
[16]	JEH G, WIDOM J.SimRank: A Measure of Structural-Context Similarity[C]// Association for Computing Machinery. Proceedings of the 8th ACM Special Interest Group on Knowledge Discovery and Data Mining International Conference, July 23-25, 2002, Edmonton, AB, Canada. New York: ACM, 2002: 538-543.
[17]	BAUML M, TAPASWI M, STIEFELHAGEN R.Semi-supervised Learning with Constraints for Person Identification in Multimedia Data[C]// IEEE Computer Society. The IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013, Portland, Oregon, American. Washington, DC, USA: IEEE Computer Society, 2013: 3602-3609.
[18]	July.动态规划算法解LCS问题[EB/OL]. .
[19]	LEVENSHTEIN V I.Binary Codes Capable of Correcting Deletions, Insertions and Reversals[J]. Soviet Physics Doklady, 1966, 10(8): 707-710.
[20]	SALTON G.The SMART Retrieval System—Experiments in Automatic Document Processing[M]. Upper Saddle River, NJ, USA: Prentice-Hall Inc., 1971.
[21]	JARO M A.Unimatch: A Record Linkage System: Users Manual[M]. Washington, USA: Bureau of the Census, 1978.

跨社交网络的实体用户关联技术研究

Research on Users Associated Technology across Social Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 21

相关文章 2

编辑推荐

Metrics

本文评价

[1]	殷卫东;朱晓华;赵俊凯. 网络舆情技术浅析[J]. , 2012, 12(3): 0-0.
[2]	戴媛;程学旗. 面向网络舆情分析的实用关键技术概述[J]. , 2008, 8(6): 0-0.